QODA enables the integration and programming of quantum processing units, GPUs, and CPUs in one system.
NVIDIA presented QODA – Quantum-Optimized Device Architecture – a platform for hybrid quantum-classical computers that enables integration and programming of quantum processing units (QPUs), GPUs, and CPUs in one system. The tech is aimed at "the programmer who wants to do algorithm research and build hybrid applications for future quantum advantage."
"QODA enables GPU-accelerated system scalability and performance across heterogeneous QPU, CPU, GPU, and emulated quantum system elements."
QODA consists of a specification and a compiler NVQ++. According to NVIDIA, it delivers a unified programming model designed for quantum processors (actual or emulated) in a hybrid setting. It supports hybrid deployments via emulation on a GPU up to NVIDIA DGX SuperPOD and with multiple QPU partner backends.
The developers promise the tech's high performance, with "287X speedup in end-to-end Variational Quantum Eigensolver (VQE) performance with 20 qubits" and improved scaling compared to Pythonic frameworks.
You can find out more on NVIDIA's website and its blog.